Merge #153475

153475: sql: add system table for external statement hints r=michae2 a=DrewKimball

#### sql: add hints package

This commit adds a new `sql/hints` package along with a `StatementHints`
protobuf struct and some utility functions for working with it.

Epic: None

Release note: None

#### sql: add system.statement_hints table

This patch adds a new table, `system.statement_hints`, which can be used to
associate "external" hints with a statement without having to modify
the statement itself. A following PR will add a per-node cache for this
table, similar to the way table stats are handled.

Informs #148160

Release note: None

Co-authored-by: Drew Kimball <drewk@cockroachlabs.com>

Author: craig[bot]

docs/generated/settings/settings-for-tenants.txt

@@ -421,4 +421,4 @@ trace.zipkin.collector	string		the address of a Zipkin instance to receive trace
 ui.database_locality_metadata.enabled	boolean	true	if enabled shows extended locality data about databases and tables in DB Console which can be expensive to compute	application
 ui.default_timezone	string		the default timezone used to format timestamps in the ui	application
 ui.display_timezone	enumeration	etc/utc	the timezone used to format timestamps in the ui. This setting is deprecatedand will be removed in a future version. Use the 'ui.default_timezone' setting instead. 'ui.default_timezone' takes precedence over this setting. [etc/utc = 0, america/new_york = 1]	application
-version	version	1000025.3-upgrading-to-1000025.4-step-012	set the active cluster version in the format '<major>.<minor>'	application
+version	version	1000025.3-upgrading-to-1000025.4-step-014	set the active cluster version in the format '<major>.<minor>'	application

docs/generated/settings/settings.html

@@ -379,6 +379,6 @@
 <tr><td><div id="setting-ui-database-locality-metadata-enabled" class="anchored"><code>ui.database_locality_metadata.enabled</code></div></td><td>boolean</td><td><code>true</code></td><td>if enabled shows extended locality data about databases and tables in DB Console which can be expensive to compute</td><td>Basic/Standard/Advanced/Self-Hosted</td></tr>
 <tr><td><div id="setting-ui-default-timezone" class="anchored"><code>ui.default_timezone</code></div></td><td>string</td><td><code></code></td><td>the default timezone used to format timestamps in the ui</td><td>Basic/Standard/Advanced/Self-Hosted</td></tr>
 <tr><td><div id="setting-ui-display-timezone" class="anchored"><code>ui.display_timezone</code></div></td><td>enumeration</td><td><code>etc/utc</code></td><td>the timezone used to format timestamps in the ui. This setting is deprecatedand will be removed in a future version. Use the &#39;ui.default_timezone&#39; setting instead. &#39;ui.default_timezone&#39; takes precedence over this setting. [etc/utc = 0, america/new_york = 1]</td><td>Basic/Standard/Advanced/Self-Hosted</td></tr>
-<tr><td><div id="setting-version" class="anchored"><code>version</code></div></td><td>version</td><td><code>1000025.3-upgrading-to-1000025.4-step-012</code></td><td>set the active cluster version in the format &#39;&lt;major&gt;.&lt;minor&gt;&#39;</td><td>Basic/Standard/Advanced/Self-Hosted</td></tr>
+<tr><td><div id="setting-version" class="anchored"><code>version</code></div></td><td>version</td><td><code>1000025.3-upgrading-to-1000025.4-step-014</code></td><td>set the active cluster version in the format &#39;&lt;major&gt;.&lt;minor&gt;&#39;</td><td>Basic/Standard/Advanced/Self-Hosted</td></tr>
 </tbody>
 </table>

pkg/BUILD.bazel

@@ -2062,6 +2062,7 @@ GO_TARGETS = [
     "//pkg/sql/gcjob:gcjob",
     "//pkg/sql/gcjob:gcjob_test",
     "//pkg/sql/gcjob_test:gcjob_test_test",
+    "//pkg/sql/hints:hints",
     "//pkg/sql/idxrecommendations:idxrecommendations",
     "//pkg/sql/idxrecommendations:idxrecommendations_test",
     "//pkg/sql/idxusage:idxusage",

pkg/backup/full_cluster_backup_restore_test.go

@@ -192,6 +192,9 @@ CREATE TABLE data2.foo (a int);
 		sqlDB.Exec(t, `CREATE SCHEDULE FOR BACKUP data.bank INTO $1 RECURRING '@hourly' FULL BACKUP ALWAYS WITH SCHEDULE OPTIONS first_run = $2`, localFoo, firstRun)
 		sqlDB.Exec(t, `PAUSE SCHEDULES SELECT id FROM [SHOW SCHEDULES FOR BACKUP]`)
 
+		// Populate system.statement_hints with a dummy row.
+		sqlDB.Exec(t, `INSERT INTO system.statement_hints (fingerprint, hint) VALUES ('FOO BAR _', '0xDEADBEEF'::BYTES)`)
+
 		injectStats(t, sqlDB, "data.bank", "id")
 		sqlDB.Exec(t, `BACKUP INTO $1`, localFoo)
 
@@ -294,6 +297,7 @@ CREATE TABLE data2.foo (a int);
 				systemschema.UITable.GetName(),
 				systemschema.UsersTable.GetName(),
 				systemschema.ScheduledJobsTable.GetName(),
+				systemschema.StatementHintsTable.GetName(),
 			}
 
 			verificationQueries := make([]string, len(systemTablesToVerify))
@@ -713,6 +717,7 @@ func TestClusterRestoreFailCleanup(t *testing.T) {
 				{"role_options"},
 				{"scheduled_jobs"},
 				{"settings"},
+				{"statement_hints"},
 				{"tenant_settings"},
 				{"ui"},
 				{"users"},
@@ -807,6 +812,7 @@ func TestClusterRestoreFailCleanup(t *testing.T) {
 				{"role_options"},
 				{"scheduled_jobs"},
 				{"settings"},
+				{"statement_hints"},
 				{"tenant_settings"},
 				{"ui"},
 				{"users"},

pkg/backup/system_schema.go

@@ -872,6 +872,9 @@ var systemTableBackupConfiguration = map[string]systemBackupConfiguration{
 	systemschema.TransactionDiagnosticsTable.GetName(): {
 		shouldIncludeInClusterBackup: optOutOfClusterBackup,
 	},
+	systemschema.StatementHintsTable.GetName(): {
+		shouldIncludeInClusterBackup: optInToClusterBackup, // No desc ID columns.
+	},
 }
 
 func rekeySystemTable(

pkg/backup/testdata/backup-restore/external-connections-nodelocal

@@ -51,6 +51,7 @@ role_options table full
 scheduled_jobs table full
 schema schema full
 settings table full
+statement_hints table full
 system database full
 ui table full
 users table full

pkg/backup/testdata/backup-restore/external-connections-userfile

@@ -51,6 +51,7 @@ role_options table full
 scheduled_jobs table full
 schema schema full
 settings table full
+statement_hints table full
 system database full
 ui table full
 userfiles_root_upload_files table full

pkg/ccl/logictestccl/testdata/logic_test/crdb_internal_tenant

@@ -251,12 +251,12 @@ txn_id  txn_fingerprint_id  query  implicit_txn  session_id  start_time  end_tim
 query ITTI
 SELECT range_id, start_pretty, end_pretty, lease_holder FROM crdb_internal.ranges
 ----
-78  /Tenant/10  /Tenant/11  1
+79  /Tenant/10  /Tenant/11  1
 
 query ITT
 SELECT range_id, start_pretty, end_pretty FROM crdb_internal.ranges_no_leases
 ----
-78  /Tenant/10  /Tenant/11
+79  /Tenant/10  /Tenant/11
 
 query IT
 SELECT zone_id, target FROM crdb_internal.zones ORDER BY 1

pkg/ccl/logictestccl/testdata/logic_test/multi_region_remote_access_error

@@ -471,7 +471,7 @@ skipif config multiregion-9node-3region-3azs-vec-off
 query I retry
 SELECT DISTINCT range_id FROM [SHOW RANGES FROM TABLE messages_rbr]
 ----
-83
+84
 
 # Update does not fail when accessing all rows in messages_rbr because lookup
 # join does not error out the lookup table in phase 1.

pkg/ccl/logictestccl/testdata/logic_test/regional_by_row_insert_fast_path

@@ -200,7 +200,7 @@ query T rowsort
 SELECT message FROM [SHOW KV TRACE FOR SESSION]
 WHERE message LIKE '%batch%' AND message LIKE '%Scan%'
 ----
-r77: sending batch 4 Scan to (n1,s1):1
+r78: sending batch 4 Scan to (n1,s1):1
 
 # Regression test for #115377.
 statement ok